Partner context: pointers to USHMM's intake workflow and the Accessioning Rationale Form

The museum's email and form, and the project's summary of them, are internal
and stay out of git like the earlier workflow note; this adds the ignore rule,
the project-kit entry and a pointer for coding agents.

Claude-Session: https://claude.ai/code/session_01AteuhwysR4rHp4fqUteLAE

.gitignore

@@ -18,4 +18,5 @@ private/*
 
 # Internal partner documents: distributed in the project-kit zip only
 project-kit/knowledge/01_curatorial_workflow.md
+project-kit/knowledge/07_ushmm_intake_workflow_and_arf.md
 project-kit/knowledge/02_design_plan.md

CLAUDE.md

@@ -11,6 +11,9 @@ CuratorBot drafts Curator Briefs for donated Holocaust oral history interviews,
 - Testimony is described soberly. Never add features that score suffering.
 - Style for prose and UI copy: no em-dashes.
 
+## Partner context
+- `project-kit/knowledge/07_ushmm_intake_workflow_and_arf.md` (internal, not in git): USHMM's oral history intake workflow (first conversation with eligibility questions, digitisation as WAV or MPEG-2/4, Box delivery, appraisal, Accessioning Rationale Form, team vote) and which ARF sections CuratorBot can draft. Appraisal (viewing and listening) is the bottleneck to relieve. Originals in `private/partner/ushmm/`.
+
 ## Layout
 - `curatorbot/transcript.py` segments (segId, start, role Q/A, text, lang, translation)
 - `curatorbot/annotate.py` spatio-textual 0.4.1 (pinned tag) on narrator turns

project-kit/README.md

@@ -6,7 +6,7 @@ Both projects get the same instructions and the same files, so when their answer
 
 1. **Create the project.** Name it `CuratorBot`. Description: "Evidence-grounded assistant for oral history intake review; hosted demo for USHMM and other partners."
 2. **Paste the instructions.** Copy all of `instructions.md` into the project's instructions (Claude: project instructions; ChatGPT: project instructions).
-3. **Add the knowledge files** from `knowledge/`. Files 01 and 02 are internal and are not in the public repository; they come in the separate project-kit download.
+3. **Add the knowledge files** from `knowledge/`. Files 01, 02 and 07 are internal and are not in the public repository; they come in the separate project-kit download.
 
    | File | What it gives the model |
    | --- | --- |
@@ -16,6 +16,7 @@ Both projects get the same instructions and the same files, so when their answer
    | `04_spatio_textual_README.md` | The library's features, CLI and output fields |
    | `05_vocabulary_demo.txt` | The closed heading list used in the demo |
    | `06_synthetic_transcript.txt` | A fictional interview to test prompts on |
+   | `07_ushmm_intake_workflow_and_arf.md` | USHMM's intake stages, the Accessioning Rationale Form section by section, and where CuratorBot fits (internal) |
 
    If your Claude plan lets you connect GitHub to project knowledge, add `SpaceTimeNarratives/curatorbot` as well, so the model sees current code.
 4. **Start one conversation per workstream** with the starters in `kickoff-prompts.md`.